Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3464 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3681. Min Range: -9.3681
Max Act: 9.3681. Min Act: -0.1700
Data Index: 452999 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3681. Min Range: -9.3681
Max Act: 8.9931. Min Act: -0.1700
Data Index: 1278197 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3681. Min Range: -9.3681
Max Act: 8.9306. Min Act: -0.1700
Data Index: 712671 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3681. Min Range: -9.3681
Max Act: 8.8056. Min Act: -0.1700
Data Index: 6534033 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3681. Min Range: -9.3681
Max Act: 8.7431. Min Act: -0.1700
Data Index: 8586386 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3681. Min Range: -9.3681
Max Act: 8.6806. Min Act: -0.1700
Data Index: 7421753 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3681. Min Range: -9.3681
Max Act: 8.6181. Min Act: -0.1700
Data Index: 110651 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3681. Min Range: -9.3681
Max Act: 8.6181. Min Act: -0.1700
Data Index: 931003 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3681. Min Range: -9.3681
Max Act: 8.6181. Min Act: -0.1700
Data Index: 1375970 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3681. Min Range: -9.3681
Max Act: 8.4931. Min Act: -0.1700
Data Index: 5871486 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3681. Min Range: -9.3681
Max Act: 8.5556. Min Act: -0.1700
Data Index: 7728294 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3681. Min Range: -9.3681
Max Act: 8.4931. Min Act: -0.1700
Data Index: 751508 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3681. Min Range: -9.3681
Max Act: 8.4931. Min Act: -0.1700
Data Index: 5024563 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3681. Min Range: -9.3681
Max Act: 8.4306. Min Act: -0.1700
Data Index: 753378 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3681. Min Range: -9.3681
Max Act: 8.4306. Min Act: -0.1700
Data Index: 507245 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3681. Min Range: -9.3681
Max Act: 8.4306. Min Act: -0.1700
Data Index: 5107214 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3681. Min Range: -9.3681
Max Act: 8.3681. Min Act: -0.1700
Data Index: 1001474 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3681. Min Range: -9.3681
Max Act: 8.3056. Min Act: -0.1700
Data Index: 648925 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3681. Min Range: -9.3681
Max Act: 8.3681. Min Act: -0.1700
Data Index: 8045316 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3681. Min Range: -9.3681
Max Act: 8.3681. Min Act: -0.1700
Data Index: 73232 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19